# Phi 3 Small 8k Instruct vs Qwen2.5-Coder-32B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-small-8k-instruct-vs-qwen2-5-coder-32b
- Last updated: 2026-10-11
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 1 category and Qwen2.5-Coder-32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Coder-32B leads 41.6 to 31.1.
- The biggest single-benchmark swing is LiveBench Coding: 20.3% for Phi 3 Small 8k Instruct and 56.9% for Qwen2.5-Coder-32B.

## Snapshot

| | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.3 | 33.4 |
| Rank | 314 | 245 |
| Context | — | 33K |
| Input $/M | — | $0.66 |
| Output $/M | — | $1 |
| Weights | Open | Open |

## Coding

- Phi 3 Small 8k Instruct: 27.9 (#318)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Coding | 20.3% | 56.9% |
| LMArena Coding | 1101 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Reasoning

- Phi 3 Small 8k Instruct: 14.8 (#323)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Reasoning | 15.9% | 42.1% |
| LMArena Hard Prompts | 1100 | 1251 |
| LiveBench Data Analysis | 30.3% | 49.9% |
| HellaSwag | 77% | 83% |
| LiveBench | 24% | 46.2% |
| WinoGrande | 81.5% | 80.8% |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| Epoch Capabilities Index | — | 119.49 |

## Math

- Phi 3 Small 8k Instruct: 27.6 (#248)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | 17.6% | 46.6% |
| LMArena Math | 1151 | 1251 |
| GSM8K | — | 93% |

## Knowledge

- Phi 3 Small 8k Instruct: 29.1 (#240)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1067 | 1221 |
| ARC (AI2) Challenge | 90.7% | 70.5% |
| MMLU | 75.7% | 79.1% |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |

## Multilingual

- Phi 3 Small 8k Instruct: 28.5 (#272)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1058 | 1205 |
| LMArena Chinese | 1061 | 1222 |
| LMArena Russian | 1111 | 1228 |
| LMArena French | 1135 | — |
| LMArena German | 1080 | — |
| LMArena Japanese | 966 | — |
| LMArena Korean | 894 | — |
| LMArena Spanish | 1111 | — |

## Instruction Following

- Phi 3 Small 8k Instruct: 51.9 (#292)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Instruction Following | 47.2% | 58.7% |
| LMArena Instruction Following | 1087 | 1223 |

## Long Context

- Phi 3 Small 8k Instruct: 33.0 (#267)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1088 | 1251 |

## Writing & Preference

- Phi 3 Small 8k Instruct: 31.1 (#284)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1110 | 1230 |
| LMArena Creative Writing | 1083 | 1174 |
| LMArena Multi-Turn | 1068 | 1222 |
| LiveBench Language | 12.9% | 23.3% |

## FAQ

### Is Phi 3 Small 8k Instruct better than Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.3 on the Noometry Index.

### Is Phi 3 Small 8k Instruct or Qwen2.5-Coder-32B better for coding?

Phi 3 Small 8k Instruct scores higher on coding benchmarks: 27.9 versus 22.6 in the Noometry coding category.

### How many benchmarks do Phi 3 Small 8k Instruct and Qwen2.5-Coder-32B share?

23 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Qwen2.5-Coder-32B has 31.